codertimo/BERT-pytorch

Health v2 · maintenance only

Adoption not part of the score

6527 stars · 1311 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch implementation of Google AI's 2018 BERT model with simple, readable code. It provides CLI tools for building vocabulary and pre-training BERT with masked language modeling and next sentence prediction on your own corpus.

Use cases

• pre-train a BERT model on my own corpus
• understand how BERT works by reading a simple implementation
• train a masked language model in pytorch
• implement next sentence prediction training
• build a vocabulary file for BERT training

When to choose

• you want a minimal, easy-to-read BERT implementation for learning or research
• you need to pre-train BERT from scratch on a custom corpus
• you prefer a lightweight pip-installable package over Hugging Face's larger ecosystem

When to avoid

• you need production-grade, well-verified transformer models with tokenizers and fine-tuning support
• you want the latest model architectures or active community maintenance
• you need multilingual or optimized inference performance

Facets

library · maturity maintenance

machine-learning nlp deep-learning machine-learning deep-learning python bert transformer language-model pytorch pretraining natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="codertimo/BERT-pytorch")